At Ciklum, working with adidas, I designed a Data Aggregation & Distribution Hub for BCTF and built its proof of concept. I also fixed split-brain and reliability defects in Akka and Hazelcast clusters; there were no cluster failures for the rest of my time on the project.
At PitchBook, I was the technical lead for moving about 300 services across 30 teams to high availability across three zones. I wrote the technical plan and migration guides, advised teams on redesigns, and moved one service’s scheduled jobs into separate Kubernetes jobs.
Since late 2025, I’ve been building RAG and agent systems through my own projects, including a production-style RAG service and an MCP server over an LLM gateway. I also lecture a master’s-level course on autonomous agent design, for which I wrote the demo code.

